MUSHY: Multimodal Flow-Based Amortized Bayesian Inference for Spectroscopic Data Fusion
Abstract
We are in an era of unprecedented spectroscopic data availability, with surveys such as APOGEE, GALAH, and DESI observing millions of stars. However, data are heterogeneous and to date, efforts to exploit synergies between surveys have been limited. In particular, there is a lack of principled methods that combine spectroscopic data from different surveys to improve inference of physical parameters. In this work we present a new method, MUSHY, for spectroscopic data fusion. MUSHY is an amortized Bayesian inference method, using a rectified flow model with multimodal inputs to learn a posterior distribution over physical parameters. Using synthetic spectra generated via ATLAS12/SYNTHE, including realistic instrumental effects and noise, we demonstrate that MUSHY can precisely infer physical parameters with well-calibrated posteriors from any combination of surveys, with multimodal inputs providing stronger constraints on the posterior than single-survey data alone. This work paves the way for principled combination of spectroscopic data from heterogeneous sources.
Related
- TNFlow: Amortized Posterior Inference for Trans-Neptunian Object Surface Composition
- ENFR: Evidence Networks with Flow-Matched References for Amortized Simulation-Based Model Inference
- Misspecification in amortized X-ray spectral inference: a detection benchmark, a gain shift three schemes cannot see, and marginalizing it out
- Solar spicule population properties inferred from IRIS Mg II k off-limb spectra using likelihood-free Bayesian inference
- Fast Bayesian Inference for Long-Duration Gravitational-Wave Signals in 3G detectors
BibTeX
@misc{shen2026mushy,
title = {{MUSHY: Multimodal Flow-Based Amortized Bayesian Inference for Spectroscopic Data Fusion}},
author = {Jeff Shen},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.15945},
eprint = {2609.15945},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.15945},
}
RIS
TY - UNPB
TI - MUSHY: Multimodal Flow-Based Amortized Bayesian Inference for Spectroscopic Data Fusion
AU - Jeff Shen
PY - 2026
DA - 2026/09/14
PB - arXiv
DO - 10.48550/arxiv.2609.15945
UR - https://arxiv.org/abs/2609.15945
AB - We are in an era of unprecedented spectroscopic data availability, with surveys such as APOGEE, GALAH, and DESI observing millions of stars. However, data are heterogeneous and to date, efforts to exploit synergies between surveys have been limited. In particular, there is a lack of principled methods that combine spectroscopic data from different surveys to improve inference of physical parameters. In this work we present a new method, MUSHY, for spectroscopic data fusion. MUSHY is an amortized Bayesian inference method, using a rectified flow model with multimodal inputs to learn a posterior distribution over physical parameters. Using synthetic spectra generated via ATLAS12/SYNTHE, including realistic instrumental effects and noise, we demonstrate that MUSHY can precisely infer physical parameters with well-calibrated posteriors from any combination of surveys, with multimodal inputs providing stronger constraints on the posterior than single-survey data alone. This work paves the way for principled combination of spectroscopic data from heterogeneous sources.
ER -